© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129294
    Prev
    Next
    INDEX
    Explanations

    unhides hidden divs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سابق
    -0.07
    可以直接
    -0.07
    不想
    -0.07
     ریکارڈ
    -0.06
     стаби
    -0.06
    好了
    -0.06
     بعد
    -0.06
     Connelly
    -0.06
    ffected
    -0.06
    ph
    -0.06
    POSITIVE LOGITS
     there
    0.06
     দুটি
    0.06
    getHeader
    0.06
    र्‍या
    0.06
     সড়
    0.06
    한편
    0.05
    বিশেষ
    0.05
     establishes
    0.05
     agility
    0.05
     grasp
    0.05
    Activations Density 0.013%

    No Known Activations